collaborators

8 papers

cs.LG2026

ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction

Hexiao Ding, Hongzhao Chen, Jing Lan +12

Accurate prediction of ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) is important for drug discovery. Most predictors use undirected molecular graphs and pa…

eess.IV2026

Decoding the Alzheimer's Continuum: Interpretable Multi-Gate Routing for Diagnosis and Transition Prediction

Yufeng Jiang, Hexiao Ding, Hongzhao Chen +8

Alzheimer's disease (AD) manifests as a continuous progression from normal cognition (NC) through mild cognitive impairment (MCI) to dementia. However, most deep learning approache…

cs.CV2026

Any-to-All MRI Synthesis: A Unified Foundation Model for Nasopharyngeal Carcinoma and Its Downstream Applications

Yao Pu, Yiming Shi, Zhenxi Zhang +6

Magnetic resonance imaging (MRI) is essential for nasopharyngeal carcinoma (NPC) radiotherapy (RT), but practical constraints, such as patient discomfort, long scan times, and high…

cs.LG2026

Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery

Jing Lan, Hexiao Ding, Hongzhao Chen +8

Accurate identification of drug-target interactions (DTI) remains a central challenge in computational pharmacology, where sequence-based methods offer scalability. This work intro…

cs.CV2026

DeepMoLM: Leveraging Visual and Geometric Structural Information for Molecule-Text Modeling

Jing Lan, Hexiao Ding, Hongzhao Chen +8

AI models for drug discovery and chemical literature mining must interpret molecular images and generate outputs consistent with 3D geometry and stereochemistry. Most molecular lan…

eess.IV2025

REACT-KD: Region-Aware Cross-modal Topological Knowledge Distillation for Interpretable Medical Image Classification

Hongzhao Chen, Hexiao Ding, Yufeng Jiang +8

Reliable and interpretable tumor classification from clinical imaging remains a core challenge. The main difficulties arise from heterogeneous modality quality, limited annotations…